# Text NLP Annotation Workbench Run explainable local tokenization, sentence splitting, stopword, lemma, stem, entity and n-gram annotation with JSONL or CoNLL export. > Canonical page: https://elysiatools.com/en/tools/text-nlp-annotation-workbench - **Category:** Text Processing - **Keywords:** NLP annotation, tokenization, POS tagging, lemmatization, stemming, NER, n-gram, CoNLL, JSONL ## Overview Text NLP Annotation Workbench analyzes pasted text with explainable local rules for tokenization, sentence splitting, stopword handling, stemming, lemmatization, entity detection, and n-grams. Review the results as JSON, JSONL, or CoNLL. ## Inputs - **Text Content** (textarea): Paste a document or corpus sample... - **Language** (select) - **Output Format** (select) - **Remove Stopwords** (checkbox) - **Enable Stemming** (checkbox) - **Enable Lemmatization** (checkbox) - **Detect Entities** (checkbox) - **N-gram Size** (number) ## When to use - Annotate a document or corpus sample before downstream NLP analysis. - Extract entities and inspect token-level text features from support, research, or business text. - Create line-oriented JSONL or CoNLL annotations for evaluation and labeling workflows. ## How it works - Paste a document or corpus sample into the Text Content field. - Choose a language or use Auto Detect. - Enable or disable stopword removal, stemming, lemmatization, and entity detection, then set an n-gram size from 1 to 3. - Select JSON, JSONL, or CoNLL to view the annotated result. ## Use cases - Prepare token and entity annotations for NLP experiments. - Inspect word forms, stems, lemmas, and n-gram patterns in multilingual text. - Export structured annotations for corpus review or line-based labeling workflows. ## Frequently asked questions ### What text can I analyze? Paste a document or corpus sample into the text input field. ### Which languages are supported? The tool supports automatic detection plus English, Chinese, Spanish, French, German, Russian, and Portuguese. ### Which output formats are available? Results can be formatted as JSON, JSONL with one token per line, or CoNLL. ### Can I disable stopword removal or linguistic annotations? Yes. You can toggle stopword removal, stemming, lemmatization, and entity detection independently. ### What n-gram sizes can I use? You can choose an n-gram size from 1 through 3. ## Related tools - [Bulk Email Extractor](https://elysiatools.com/en/tools/bulk-email-extractor): Extract all email addresses from input text, articles, web source code, or mixed content. Supports deduplication and export to JSON. - [Text Encoding Forensics and Repair](https://elysiatools.com/en/tools/text-encoding-forensics-and-repair): Inspect text encoding, BOM, newline style and mojibake symptoms, then produce a scored local repair candidate. - [Unlimited AI Multi-Language Title Translator](https://elysiatools.com/en/tools/unlimited-ai-title-translator-multi): Professional AI-powered multi-language title translator for movies, TV shows, anime, games, and more with JSON output - [BOM Character Remover](https://elysiatools.com/en/tools/data-bom-remover): Remove BOM (Byte Order Mark) characters from text and file content. Perfect for cleaning up text files that have encoding issues, fixing CSV imports, and preparing data for processing. Features: - Detect and remove UTF-8 BOM (EF BB BF) - Detect and remove UTF-16 BOM (FE FF or FF FE) - Detect and remove UTF-32 BOM (00 00 FE FF or FF FE 00 00) - Support multiple input formats - Visual BOM character display - Detailed detection report - Support for batch text processing Common Use Cases: - Fix CSV file import errors - Clean up text file encoding issues - Prepare data for JSON parsing - Fix XML parsing problems - Resolve API data encoding conflicts - Standardize text data format - [Remove Duplicate Lines](https://elysiatools.com/en/tools/remove-duplicate-lines): Deduplicate lines in a list or text block. Keep the first or last occurrence, with options for case sensitivity, whitespace trimming, and dropping empty lines. - [JSON Diff Visualizer](https://elysiatools.com/en/tools/json-diff-visualizer): Compare two JSON payloads and render a visual HTML diff with path-level additions, removals, changes, and statistics - [JSON Key Extractor](https://elysiatools.com/en/tools/json-key-extractor): Extract all keys from JSON objects with multiple output formats. Perfect for analyzing JSON structure, documentation generation, and understanding complex nested objects. - [Uniq With](https://elysiatools.com/en/tools/uniq-with): Remove duplicates using lodash _.uniqWith and deep equality ## Samples - [Text with Emoji Samples](https://elysiatools.com/en/samples/text-with-emoji-samples): Mixed language text containing various Unicode emojis for testing emoji extraction - [Duplicate Line Samples](https://elysiatools.com/en/samples/text-duplicate-line-samples): Sample files with various types of duplicate lines for testing duplicate removal tools - [Special Characters Samples](https://elysiatools.com/en/samples/text-special-characters-samples): Sample text files with various special characters, punctuation, and symbols for testing non-alphanumeric character removal - [Android File Operations Java Samples](https://elysiatools.com/en/samples/android-file-operations-java): Android Java file operations examples including text file read/write, file copy/move, directory traversal, and file validation